Files
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

79 lines
2.2 KiB
C++

#include "test_framework.hpp"
#include <vector>
// LDS bank conflict test - stride-32 access pattern
// Targets SQ_LDS_BANK_CONFLICT counter
__global__ void lds_conflicts_kernel(float* output, const float* input) {
__shared__ float shared_mem[1024];
int tid = threadIdx.x;
int gid = blockIdx.x * blockDim.x + threadIdx.x;
// Write with stride to cause bank conflicts
// On AMD GPUs, LDS has 32 banks
int write_idx = (tid * 32) % 1024;
shared_mem[write_idx] = input[gid];
__syncthreads();
// Read with stride to cause bank conflicts
int read_idx = (tid * 32 + 1) % 1024;
float val = shared_mem[read_idx];
// Multiple rounds of conflicting access
for (int i = 0; i < 10; i++) {
write_idx = ((tid + i) * 32) % 1024;
shared_mem[write_idx] = val * 1.01f;
__syncthreads();
read_idx = ((tid + i + 1) * 32) % 1024;
val = shared_mem[read_idx];
__syncthreads();
}
output[gid] = val;
}
class LDSConflictsTest : public test_framework::TestBase {
public:
LDSConflictsTest() : TestBase("LDS Conflicts - Bank Conflicts") {}
bool setup() override {
size_ = 256 * 1024; // 256K elements
// Allocate device memory
d_input_ = hip_utils::allocateDeviceWithValue<float>(size_, 1.0f);
d_output_ = hip_utils::allocateDevice<float>(size_);
std::cout << " Array size: " << size_ << " elements" << std::endl;
std::cout << " LDS size per block: 1024 floats (4 KB)" << std::endl;
std::cout << " Access pattern: stride-32 (causes bank conflicts)" << std::endl;
return true;
}
bool execute() override {
dim3 block_size(256);
dim3 grid_size(size_ / block_size.x);
test_framework::KernelRunner runner("lds_conflicts_kernel", grid_size, block_size);
runner.launch(lds_conflicts_kernel, d_output_, d_input_);
return true;
}
void cleanup() override {
hip_utils::freeDevice(d_input_);
hip_utils::freeDevice(d_output_);
}
private:
float* d_input_ = nullptr;
float* d_output_ = nullptr;
size_t size_;
};
int main() {
LDSConflictsTest test;
return test.run();
}